AFF/Demos/Ghostlyn · AI agents at Maria 01
Ghostlyn Workshops·Tailored · 1 day · On-site or remote

Your team, shipping real AI agents — by Friday.

A hands-on workshop run by Oleg Podsechin — the engineer behind Ghostlyn and ten years of Toughbyte. Cuts through the agent hype, maps it onto your workflows, and leaves your team with a working prototype they actually use on Monday.

Book a workshop
From€1,950
Why Ghostlyn

Built by people who ship agents — not people who tweet about them.

A team-first agent harness

Ghostlyn is model-agnostic — DeepSeek, Claude, OpenAI, open-weight, switch mid-run. Built for teams: shared skills, shared tools, shared memory.

Engineering rigor

Vercel AI under the hood. Progressive disclosure for skills. Sub-agent fan-out for parallel work. Structured memory tables, not just markdown.

Tailored to your stack

Most workshops are generic. Ours starts with a discovery call. We build the workshop around the workflows you actually want to automate.

Capabilities your team will leave with

Six concrete things, not vibes.

01
Tool design & function-calling

How to define the name, description and parameters so the model actually picks the right tool — and how to spot when it won't.

02
Context engineering

Million-token windows fill fast. Compaction discipline, sub-agents, fresh chats per task, offloading state to files.

03
Skills & MCP packaging

Bundle expertise into SKILL.md folders with progressive disclosure. When to skill, when to MCP, when to just prompt.

04
RAG & memory

Grep, full-text, embeddings. Structured local tables vs unstructured files. Stopping hallucinations with grounded retrieval.

05
Safety & the lethal trifecta

Private data + untrusted content + external comms = RCE. Permission modes, auto-mode monitors, blast-radius design.

06
Workflow vs agent decisioning

When code-driving-LLM beats LLM-driving-code. Answer agents vs act agents. Human-in-the-loop drafting patterns.

A day in the room

Five modules. One working prototype.

The exact agenda is shaped by your discovery call. This is the spine we work from.

  1. M01
    Foundations — what an agent actually is

    Model, harness, tools, context. The agentic loop. Why the model isn't the bottleneck anymore.

  2. M02
    Your LLM mental model

    Next-token prediction, hallucination, memory-as-illusion. Sizing the right model for the job — proprietary vs open-weight cost math.

  3. M03
    Building blocks & tools

    Function calling, web fetch, code execution, MCP. Designing tools the model can use without supervision.

  4. M04
    Architectures & safety

    Skills with progressive disclosure, sub-agent fan-out, the lethal trifecta, permission modes, the auto-mode monitor pattern.

  5. M05
    Hands-on with Ghostlyn

    Pick a real workflow from your team. Build it end-to-end on Ghostlyn against your data. Ship it.

Target outcomes

By the end of the day, your team can…

  • Run a sane discovery on which workflows are actually worth automating (and which are vanity demos).
  • Build, deploy and iterate on a Ghostlyn agent against their own data.
  • Tell when a problem wants a workflow vs an agent — and design accordingly.
  • Spot the lethal trifecta in a proposed design before it ships.
  • Manage context windows, skills and sub-agents like senior practitioners.
Who it's for

Teams who are past “ChatGPT for everyone”.

Engineering leaders

rolling out agents internally and tired of unmaintained demos.

Product teams

rethinking the product workflow now that LLMs are in the loop.

Ops & RevOps

automating repetitive, judgment-light parts of the funnel.

Founders

validating where AI actually changes the unit economics.

O
Your instructor

Oleg Podsechin

Founder of Toughbyte (10 years). Builder of Ghostlyn, a team-first AI work assistant. Built one of the earliest mobile multiplayer games — pre-home-computer. Has been writing software since before stack overflow had a stack to overflow. Spends his days shipping agents that companies actually use.

Let's run one

A working agent, in your team's hands, by the end of the day.

Tailored Ghostlyn Workshops from €1,950. One day, six to twelve people, your stack, your data, your workflow. Reply to a short discovery email — we take it from there.

Book a workshop
hello@ghostlyn.com

Workshops · Q&A

Questions about the workshops

A tailored, one-day, hands-on workshop run by Oleg Podsechin. Your team brings a real use case from your stack and ends the day with a working AI agent built on Ghostlyn.

From €1,950, depending on team size and scope. The price covers preparation, the on-site day, and follow-up to get the agent into production.

A mixed group works best — engineers, product, and one or two people who own the workflow being automated. You do not need prior AI experience.

A working agent in your environment, a shared mental model for evaluating and trusting agents, and a clear next step for rolling them out across the team.